Knowledge catalogue
arXiv:2610.19934v1 Announce Type: new Abstract: Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much
arXiv:2610.18924v1 Announce Type: cross Abstract: Interpreting electron paramagnetic resonance (EPR) spectra commonly requires repeated forward simulation and optimization of spin Hamiltonian paramete
arXiv:2610.19492v1 Announce Type: new Abstract: Streaming Inverse Text Normalization (ITN) is vital for converting spoken-form outputs from streaming Automatic Speech Recognition into formatted writte
arXiv:2610.19041v1 Announce Type: cross Abstract: Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve in
arXiv:2610.20401v1 Announce Type: new Abstract: Reinforcement learning makes language models better at solving tasks, but the same mechanism also rewards guessing. When success is the only way to earn
arXiv:2610.15227v1 Announce Type: new Abstract: Unified vision-language models (VLMs) perform both text-to-image (T2I) and image-to-text (I2T) generation with one shared Transformer backbone, yet how
arXiv:2610.15231v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) models, particularly large language models (LLMs), are increasingly used in educational settings for tasks su
arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommend
arXiv:2610.19298v1 Announce Type: new Abstract: Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A progra
arXiv:2501.12375v4 Announce Type: replace Abstract: Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal i
arXiv:2610.20333v1 Announce Type: new Abstract: Controlling an agent in an environment solely perceived through onboard vision is challenging: perception yields noisy, variable-length, and partially o
arXiv:2610.20104v1 Announce Type: new Abstract: Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure.
Small teams, short runway, and constant pressure to ship faster — it’s the reality we see every day among the founders we work with at Google for Startups. When you are building a company from the gro
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to o
arXiv:2610.17365v1 Announce Type: new Abstract: As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent
arXiv:2610.16692v1 Announce Type: new Abstract: We address the Cross-View Object Re-Identification (ReID) task, aiming to match identities across drastically different viewpoints. We focus on Single-V
Just saw this demo from OpenBMB for MiniCPM-V 4.7, and the on-device capability is pretty impressive. A 35B-A3B MoE vision-language model running locally on mobile devices is already interesting, but
arXiv:2610.16275v1 Announce Type: new Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive
arXiv:2610.14553v1 Announce Type: new Abstract: Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the
arXiv:2610.15488v1 Announce Type: cross Abstract: Formulaic alpha mining seeks interpretable expressions that rank assets by future returns. The task is challenging because it demands simultaneous pro
arXiv:2610.15368v1 Announce Type: new Abstract: Rapid advances in large language models have made software engineering agents capable of tackling complex coding tasks. Within a containerized environme
arXiv:2610.16440v1 Announce Type: new Abstract: Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions. Although rece
arXiv:2602.16356v2 Announce Type: replace-cross Abstract: Semantic scene understanding has enabled robots to reason and perform affordance-driven object interaction. Despite this, real-world manipulat
arXiv:2610.14005v1 Announce Type: cross Abstract: Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or satu
arXiv:2610.16985v1 Announce Type: new Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in
arXiv:2603.14701v2 Announce Type: replace Abstract: Robust depth completion is fundamental to real-world 3D scene understanding, yet existing RGB--LiDAR fusion methods degrade significantly under adve
arXiv:2610.14155v1 Announce Type: cross Abstract: Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pr
arXiv:2610.14017v1 Announce Type: cross Abstract: We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without addi
arXiv:2610.15330v1 Announce Type: new Abstract: Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation i
arXiv:1808.02932v5 Announce Type: replace-cross Abstract: In stochastic multi-armed bandits, rewards are generated by an unknown distribution; the world's reward uncertainty induces the exploration-ex
arXiv:2610.14024v1 Announce Type: new Abstract: Physics time-series data are central to fundamental discoveries involving dark matter, neutrinos, and gravitational waves. Machine learning has shown st
arXiv:2610.16105v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can y
arXiv:2610.18399v1 Announce Type: new Abstract: Visual token pruning for multimodal large language models (MLLMs) appears highly effective, with existing methods retaining over 95% of unpruned perform
arXiv:2610.14261v1 Announce Type: new Abstract: Whole-slide images (WSIs) are gigapixel-scale digital scans of histopathology tissue and serve as the primary basis for cancer diagnosis. Existing histo
arXiv:2610.17412v1 Announce Type: new Abstract: Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens indepen
arXiv:2509.02003v2 Announce Type: replace Abstract: Markov chain Monte Carlo is one of the most useful tools for obtaining samples from complex distributions, such as posterior distributions in Bayesi
arXiv:2610.17526v1 Announce Type: new Abstract: World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outpe
arXiv:2610.18658v1 Announce Type: new Abstract: Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reuse
arXiv:2610.14746v1 Announce Type: cross Abstract: World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action
arXiv:2610.17457v1 Announce Type: cross Abstract: Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious
arXiv:2610.14720v1 Announce Type: new Abstract: World Action Models (WAMs) combine action generation with future prediction, allowing predicted futures to support action evaluation and robot decision
arXiv:2610.14226v1 Announce Type: new Abstract: Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. M
arXiv:2610.17190v1 Announce Type: new Abstract: Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environme
arXiv:2610.14676v1 Announce Type: new Abstract: We present CAST-ASD (Causal Attention over Speakers and Time), a causal joint model for active speaker detection (ASD). Recent ASD models improve perfor
arXiv:2602.23541v3 Announce Type: replace-cross Abstract: Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data b
arXiv:2610.14989v1 Announce Type: new Abstract: Prior-data fitted networks (PFNs) are transformers pretrained on simulated datasets to approximate Bayesian posterior predictive distributions. Standard
arXiv:2610.14564v1 Announce Type: cross Abstract: Model-based reinforcement learning has shown superior sample efficiency by leveraging the learned latent dynamics either in the form of derivative-fre
arXiv:2506.17585v4 Announce Type: replace-cross Abstract: Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving d
arXiv:2610.16040v1 Announce Type: cross Abstract: We propose a conservative local neural operator (CLNO) for accurate and generalizable autoregressive prediction of compressible flows. Building upon t
arXiv:2506.15468v2 Announce Type: replace-cross Abstract: We propose co-creative learning as a novel paradigm where humans and AI, i.e., biological and artificial agents, mutually integrate their part
arXiv:2610.17651v1 Announce Type: cross Abstract: Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact
arXiv:2610.18850v1 Announce Type: new Abstract: Collaborative planning under operational constraints is essential for heterogeneous robot teams in large-scale missions. Unmanned Aerial Vehicles (UAVs)
arXiv:2610.16908v1 Announce Type: new Abstract: End-to-end driving requires rich spatiotemporal representations to support scene understanding and trajectory planning under strict latency constraints.
Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’
arXiv:2610.16316v1 Announce Type: new Abstract: Articulated object manipulation tasks such as opening doors, tightening bolts, and pulling drawers impose kinematic constraints on a robot end-effector'
arXiv:2610.18741v1 Announce Type: new Abstract: Reliable detection of pedestrians and road users is essential for the safe operation of autonomous vehicles. However, this task becomes increasingly cha
arXiv:2603.23356v2 Announce Type: replace-cross Abstract: We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predict
arXiv:2610.17114v1 Announce Type: new Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, hel
arXiv:2510.21974v3 Announce Type: replace Abstract: We introduce Deep Jump Gaussian Processes (DJGP), a novel method for surrogate modeling of a piecewise continuous function on a high-dimensional dom
arXiv:2610.16529v1 Announce Type: new Abstract: Plant fibers are increasingly used as sustainable reinforcements in composites, but the intrinsic variability of their microstructure causes substantial